Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing the side-effect scope: messages and usage travel with the number, which the schema does not express. It still omits what happens to a prior customer's attribution and whether the operation can fail partway.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.